Optimize with Hyperactive¶

Home

Install¶

In [ ]:

!pip install hyperactive
# Re-install pandas 2.2
!pip install --upgrade pandas

!pip install hyperactive # Re-install pandas 2.2 !pip install --upgrade pandas

Sample strategy¶

In [1]:

# import talib.abstract as ta

from lettrade import DataFeed, Strategy, crossover, crossunder
from lettrade.exchange.backtest import ForexBackTestAccount, let_backtest
from lettrade.indicator.vendor.qtpylib import inject_indicators

inject_indicators()


class SmaCross(Strategy):
    ema1_period = 9
    ema2_period = 21

    def indicators(self, df: DataFeed):
        # df["ema1"] = ta.EMA(df, timeperiod=self.ema1_period)
        # df["ema2"] = ta.EMA(df, timeperiod=self.ema2_period)
        df["ema1"] = df.close.ema(window=self.ema1_period)
        df["ema2"] = df.close.ema(window=self.ema2_period)

        df["signal_ema_crossover"] = crossover(df.ema1, df.ema2)
        df["signal_ema_crossunder"] = crossunder(df.ema1, df.ema2)

    def next(self, df: DataFeed):
        if len(self.orders) > 0 or len(self.trades) > 0:
            return

        if df.l.signal_ema_crossover[-1]:
            price = df.l.close[-1]
            self.buy(size=0.1, sl=price - 0.001, tp=price + 0.001)
        elif df.l.signal_ema_crossunder[-1]:
            price = df.l.close[-1]
            self.sell(size=0.1, sl=price + 0.001, tp=price - 0.001)


lt = let_backtest(
    strategy=SmaCross,
    datas="example/data/data/EURUSD_5m_0_10000.csv",
    account=ForexBackTestAccount,
    # plotter=None,
)

# import talib.abstract as ta from lettrade import DataFeed, Strategy, crossover, crossunder from lettrade.exchange.backtest import ForexBackTestAccount, let_backtest from lettrade.indicator.vendor.qtpylib import inject_indicators inject_indicators() class SmaCross(Strategy): ema1_period = 9 ema2_period = 21 def indicators(self, df: DataFeed): # df["ema1"] = ta.EMA(df, timeperiod=self.ema1_period) # df["ema2"] = ta.EMA(df, timeperiod=self.ema2_period) df["ema1"] = df.close.ema(window=self.ema1_period) df["ema2"] = df.close.ema(window=self.ema2_period) df["signal_ema_crossover"] = crossover(df.ema1, df.ema2) df["signal_ema_crossunder"] = crossunder(df.ema1, df.ema2) def next(self, df: DataFeed): if len(self.orders) > 0 or len(self.trades) > 0: return if df.l.signal_ema_crossover[-1]: price = df.l.close[-1] self.buy(size=0.1, sl=price - 0.001, tp=price + 0.001) elif df.l.signal_ema_crossunder[-1]: price = df.l.close[-1] self.sell(size=0.1, sl=price + 0.001, tp=price - 0.001) lt = let_backtest( strategy=SmaCross, datas="example/data/data/EURUSD_5m_0_10000.csv", account=ForexBackTestAccount, # plotter=None, )

Example¶

In [2]:

from hyperactive import Hyperactive
from hyperactive.optimizers import HillClimbingOptimizer


# define the model in a function
def params_parser(args):
    params = [
        ("ema1_period", int(args["ema1_period"])),
        ("ema2_period", int(args["ema2_period"])),
    ]
    return params


def result_parser(result):
    return result["equity"]


model = lt.optimize_model(
    params_parser=params_parser,
    result_parser=result_parser,
    fork_data=True,
)

# search space determines the ranges of parameters you want the optimizer to search through
search_space = {
    "ema1_period": list(range(5, 25, 1)),
    "ema2_period": list(range(10, 50)),
}

optimizer = HillClimbingOptimizer(epsilon=0.1, distribution="laplace", n_neighbours=4)

# start the optimization run
hyper = Hyperactive()
hyper.add_search(model, search_space, optimizer=optimizer, n_iter=1000)
hyper.run()

from hyperactive import Hyperactive from hyperactive.optimizers import HillClimbingOptimizer # define the model in a function def params_parser(args): params = [ ("ema1_period", int(args["ema1_period"])), ("ema2_period", int(args["ema2_period"])), ] return params def result_parser(result): return result["equity"] model = lt.optimize_model( params_parser=params_parser, result_parser=result_parser, fork_data=True, ) # search space determines the ranges of parameters you want the optimizer to search through search_space = { "ema1_period": list(range(5, 25, 1)), "ema2_period": list(range(10, 50)), } optimizer = HillClimbingOptimizer(epsilon=0.1, distribution="laplace", n_neighbours=4) # start the optimization run hyper = Hyperactive() hyper.add_search(model, search_space, optimizer=optimizer, n_iter=1000) hyper.run()

[0] _optimize_model (Hill Climbing): 100%|──────────| 1000/1000 [01:11<00:00, 13.89it/s, best_iter=0, best_pos=[9 0], best_score=1183.88]

Results: '_optimize_model'  
   Best score: 1183.88  
   Best parameter set:
      'ema1_period' : 14.0  
      'ema2_period' : 10.0  
   Best iteration: 0  
 
   Random seed: 2030058944  
 
   Evaluation time   : 70.76888489723206 sec    [99.86 %]
   Optimization time : 0.09942197799682617 sec    [0.14 %]
   Iteration time    : 70.86830687522888 sec    [14.11 iter/sec]
 

In [3]:

df = hyper.search_data(model)
df

df = hyper.search_data(model) df

Out[3]:

	ema1_period	ema2_period	score
0	19	47	939.08
1	14	22	821.08
2	11	23	851.68
3	11	36	940.68
4	17	23	959.68
...	...	...	...
995	20	37	904.68
996	15	12	1039.58
997	5	20	840.68
998	14	11	1170.48
999	8	14	810.48

1000 rows × 3 columns

Plot¶

Init Plotly environment¶

In [4]:

import plotly.io as pio

pio.renderers.default = "notebook"
pio.templates.default = "plotly_dark"

import plotly.io as pio pio.renderers.default = "notebook" pio.templates.default = "plotly_dark"

Type 1¶

In [5]:

import plotly.express as px

fig = px.density_heatmap(
    df,
    x="ema1_period",
    y="ema2_period",
    z="score",
    nbinsx=30,
    nbinsy=30,
    histfunc="max",
    color_continuous_scale="Viridis",
)
fig.show()

import plotly.express as px fig = px.density_heatmap( df, x="ema1_period", y="ema2_period", z="score", nbinsx=30, nbinsy=30, histfunc="max", color_continuous_scale="Viridis", ) fig.show()

Type 2¶

In [6]:

import plotly.express as px

fig = px.density_contour(
    df,
    x="ema1_period",
    y="ema2_period",
    z="score",
    histfunc="max",
)
fig.update_traces(contours_coloring="fill", contours_showlabels=True)
fig.show()

import plotly.express as px fig = px.density_contour( df, x="ema1_period", y="ema2_period", z="score", histfunc="max", ) fig.update_traces(contours_coloring="fill", contours_showlabels=True) fig.show()